Glean 拾遗
Recent picks

5picks · chronological

11-15

Why Cloud Agents ignore /poteto-mode — and how to vendor pstack

A field guide to running pstack (Lauren Tan's engineering-standard plugin) across Cursor's split setup: Grok Bot coordinates and spawns, Cloud Agents do the work in isolated VMs and open PRs. The failure mode it targets: account plugins and ~/.cursor/skills are not copied to the cloud VM, so /poteto-mode silently never loads. Fix is to sparse-checkout pstack's skills/ and agents/ and rsync them into the repo's .cursor/skills and .cursor/agents, keep those paths tracked in git, and give each runnable app its own verify-<app> skill so verification means launch/drive/evidence instead of the model asserting it looks fine. Also covers coordinator prompt templates, the permission gap between Autopilot-stack and Autopilot-full (the latter needs a fresh verifier's clean verdict before merge), and a pitfall list. For engineers already running Cloud Agents who want skill distribution and verification pinned down.

x.com · 9 min · Agent Harness · Agent Skills · Coding Agents
11-14

Cursor's plugin spec and official plugin catalog for agent skills

A Cursor-maintained plugin specification plus a catalog of official plugins. Each plugin is described by a plugin.json manifest (name, author, category) and bundles skills, commands, scripts, or connectors into units an agent can invoke directly. The collection splits into two halves: developer-workflow plugins (PR review canvases, parallel subagent orchestration, CLI patterns agents can run reliably, scaffolding and validation via create-plugin) and integrations that expose external systems such as GitHub, Playwright, BigQuery, Salesforce and Gmail to the agent. Useful if you are packaging reusable capabilities for coding agents, or want a reference for how the vendor structures and distributes them.

github.com · 15 min · Agent Skills · Cursor · Developer Tools
07-18

What we’ve learned building cloud agents

Cursor shares one year of lessons from building cloud agents. The biggest takeaway: a cloud agent's output quality depends almost entirely on having a full development environment. Unlike local agents that inherit your laptop's environment, cloud agents need it reconstructed from scratch. This led to building VM hibernation/resumption pipelines, checkpoint/restore/fork mechanisms, secret redaction, network policies, and credential management — essentially enterprise IT for agents. For reliability, early work-stealing architecture managed only one 9 of uptime. Migrating to Temporal's durable execution framework pushed past two 9s, handling over 50 million actions per day across 7 million+ unique workflows, with 40%+ of Cursor's own PRs now coming from cloud agents. Critical architectural decision: decoupling agent loop, machine state, and conversation state allows agents to run across different pod types and subagents to outlive parents. Another insight: as models improve, move logic out of the hardcoded harness into tools the agent controls (e.g., GitHub CLI, Playwright). The post also discusses current harness for computer use and future self-healing environments (autoinstall).

cursor.com · 11 min · Agent Architecture · Agent Infrastructure · Agents
07-06

Development environments for your cloud agents

Cursor ships new tools for cloud agent development environments: multi-repo support, Dockerfile-as-config with build secrets and 70% faster layered caching, agent-led setup validation, and environment-level governance (version history, audit logs, per-environment egress/secrets scoping). Enterprise teams can run fleets of parallelized agents that handle tasks end-to-end inside fully controlled environments. On config failure, agents fall back to a base image to keep running.

cursor.com · 6 min · Agent Environment · Cursor · Dockerfile
07-03

Continually Improving Our Agent Harness

Cursor shares how it continuously improves its agent harness, covering context window evolution from static to dynamic fetching, a two-layer evaluation system (offline benchmarks and online A/B tests measuring code keep rate and user satisfaction), tool call error classification and repair pipeline (anomaly detection + automated log analysis with Cloud Agents), per-model customization of tool formats and prompts (e.g., patch vs. string replacement), and mid-chat model switching with specialized instructions. The post concludes with a vision of multi-agent architectures where the harness orchestrates specialized sub-agents.

cursor.com · 13 min · Agent Engineering · Ai Tooling · Context Engineering